TFT比LSTM更擅长模拟河流流量变化，尤其在峰值和中段表现更好。
Efficacy of Temporal Fusion Transformers for Runoff Simulation
- 用TFT替代LSTM建模降雨-径流过程，结合注意力与循环机制
- 在531个美国流域上，TFT对水文曲线中段和峰值的模拟精度略高
- 可解释性强，能识别关键动态/静态变量，适合科研分析
将注意力机制与循环结构结合在序列建模中已被证明有效，尤其在水文预测领域。本文比较了时间融合变压器（Temporal Fusion Transformers, TFT）与长短期记忆网络（LSTM）在降雨-径流建模中的表现。我们在美国531个CAMELS流域上训练了十组随机初始化的TFT和LSTM模型，并在包含美国、澳大利亚、巴西、英国和智利的五个子集的Caravan数据集上重复实验。评估了模型性能、对流域属性的敏感性以及不同数据集间的差异。结果表明，TFT在模拟水文曲线中段和峰值时表现略优于LSTM，且能更好地处理更长序列，更适合大流域或高复杂度区域。作为可解释的人工智能方法，TFT能识别关键动态与静态变量，提供科学洞见。但两者在Caravan数据集上均出现显著性能下降，暗示可能存在数据质量问题。总体而言，研究突显了TFT在提升水文建模与理解方面的潜力。
原文摘要 · Abstract (English)
Combining attention with recurrence has shown to be valuable in sequence modeling, including hydrological predictions. Here, we explore the strength of Temporal Fusion Transformers (TFTs) over Long Short-Term Memory (LSTM) networks in rainfall-runoff modeling. We train ten randomly initialized models, TFT and LSTM, for 531 CAMELS catchments in the US. We repeat the experiment with five subsets of the Caravan dataset, each representing catchments in the US, Australia, Brazil, Great Britain, and Chile. Then, the performance of the models, their variability regarding the catchment attributes, and the difference according to the datasets are assessed. Our findings show that TFT slightly outperforms LSTM, especially in simulating the midsection and peak of hydrographs. Furthermore, we show the ability of TFT to handle longer sequences and why it can be a better candidate for higher or larger catchments. Being an explainable AI technique, TFT identifies the key dynamic and static variables, providing valuable scientific insights. However, both TFT and LSTM exhibit a considerable drop in performance with the Caravan dataset, indicating possible data quality issues. Overall, the study highlights the potential of TFT in improving hydrological modeling and understanding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。